OV - Compare Functions

Functions

▶sgemm.cpp: 138 - 198.30 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default							Run aocc_8							Run icx_1
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 205-206 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 220-220 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 805-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 853-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 205-206 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 220-221 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 805-821 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 853-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 205-206 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 220-221 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 805-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 853-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
411	0.49	0.05	0.07	96	0.19	0.02	413	65.33	6.04	8.33	96	22.45	2.09	418	65.38	6.03	8.28	96	22.68	2.10
415	65.97	6.10	8.32	96	22.54	2.10	409	0.58	0.05	0.08	96	0.20	0.02	414	0.56	0.05	0.08	96	0.18	0.02

▶<unknown>: 0 - 120.58 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run icx_default							Run aocc_8							Run icx_1

1018	0.00	0.00	0.01	4	0.00	0.00	1642	0.00	0.00	0.01	1	0.00	0.00	2486	0.00	0.00	0.01	3	0.00	0.00	2812	0.00	0.00	0.00	1	0.00	0.00
1401	0.02	0.00	0.04	22	0.09	0.01	1715	0.00	0.00	0.00	1	0.00	0.00	1039	0.00	0.00	0.01	1	0.00	0.00	2875	0.00	0.00	0.02	1	0.00	0.00
1405	0.00	0.00	0.01	1	0.00	0.00	1675	0.00	0.00	0.01	1	0.00	0.00	1401	0.02	0.00	0.01	27	0.03	0.00	2997	0.00	0.00	0.00	1	0.00	0.00
1385	14.42	1.33	3.78	96	10.39	0.95	1683	0.00	0.00	0.00	1	0.00	0.00	1405	0.00	0.00	0.01	2	0.00	0.00	2885	0.00	0.00	0.02	1	0.00	0.00
941	0.00	0.00	0.01	1	0.00	0.00	1680	0.00	0.00	0.00	1	0.00	0.00	1406	0.00	0.00	0.00	1	0.00	0.00	2822	0.00	0.00	0.00	1	0.00	0.00
979	0.00	0.00	0.00	1	0.00	0.00	1639	0.00	0.00	0.00	1	0.00	0.00	86	0.00	0.00	0.00	2	0.00	0.00	2879	0.00	0.00	0.01	1	0.00	0.00
1301	0.00	0.00	0.01	3	0.00	0.00	2	0.00	0.00	0.01	3	0.00	0.00	1385	14.27	1.32	3.61	96	10.06	0.91	2	0.00	0.00	0.01	4	0.00	0.00
2486	0.00	0.00	0.01	1	0.00	0.00	2355	0.00	0.00	0.00	1	0.00	0.00	786	0.00	0.00	0.00	2	0.00	0.00	2355	0.00	0.00	0.01	3	0.00	0.00
1284	0.00	0.00	0.00	1	0.00	0.00	2029	0.00	0.00	0.01	2	0.00	0.00	941	0.00	0.00	0.01	3	0.00	0.00	2018	0.00	0.00	0.00	1	0.00	0.00
789	0.00	0.00	0.01	1	0.00	0.00	1088	0.02	0.00	0.03	26	0.05	0.00	2487	17.67	1.63	4.66	96	12.51	1.14	2029	0.00	0.00	0.00	2	0.00	0.00
1323	0.00	0.00	0.00	1	0.00	0.00	1092	0.08	0.01	0.14	31	0.32	0.03	1386	0.78	0.07	2.43	92	3.07	0.28	1088	0.03	0.00	0.04	34	0.07	0.01
2487	17.27	1.60	4.55	96	12.32	1.12	1098	0.22	0.02	0.09	93	0.20	0.02	1018	0.00	0.00	0.01	8	0.00	0.00	1092	0.07	0.01	0.08	35	0.21	0.02
807	0.00	0.00	0.00	6	0.00	0.00	1111	31.36	2.90	8.11	96	21.95	2.00	807	0.01	0.00	0.01	11	0.00	0.00	1098	0.21	0.02	0.10	80	0.26	0.02
1386	0.55	0.05	1.29	89	1.56	0.14	1114	0.03	0.00	0.04	21	0.10	0.01	1301	0.00	0.00	0.01	5	0.02	0.00	2044	0.00	0.00	0.00	3	0.00	0.00
786	0.00	0.00	0.01	2	0.00	0.00	1116	0.89	0.08	0.22	96	0.61	0.06	1874	0.00	0.00	0.00	2	0.00	0.00	1104	0.00	0.00	0.01	1	0.00	0.00
1039	0.00	0.00	0.01	2	0.00	0.00	1420	0.00	0.00	0.00	1	0.00	0.00	272	0.00	0.00	0.01	4	0.00	0.00	1111	19.11	1.81	3.31	96	9.31	0.87
1874	0.00	0.00	0.01	1	0.00	0.00	1972	0.00	0.00	0.01	3	0.00	0.00	27	0.09	0.01	0.04	77	0.07	0.01	1114	0.03	0.00	0.05	21	0.13	0.01
34	0.07	0.01	0.03	69	0.05	0.00	1982	0.00	0.00	0.00	1	0.00	0.00	244	0.02	0.00	0.04	18	0.12	0.01	1116	0.62	0.06	0.14	96	0.33	0.03
265	0.01	0.00	0.09	4	0.44	0.04	2915	0.00	0.00	0.01	1	0.00	0.00	300	0.00	0.00	0.00	1	0.00	0.00	1164	0.00	0.00	0.00	2	0.00	0.00
30	0.00	0.00	0.00	1	0.00	0.00	1984	0.00	0.00	0.01	4	0.00	0.00	35	0.07	0.01	0.03	70	0.06	0.01	1972	0.00	0.00	0.01	3	0.00	0.00
269	0.00	0.00	0.01	3	0.00	0.00	1187	0.00	0.00	0.01	6	0.00	0.00	5	0.00	0.00	0.01	2	0.00	0.00	2924	0.02	0.00	0.02	29	0.03	0.00
65	0.00	0.00	0.01	4	0.00	0.00	2399	0.00	0.00	0.01	6	0.00	0.00	246	0.03	0.00	0.04	35	0.06	0.01	1984	0.00	0.00	0.01	6	0.02	0.00
355	0.01	0.00	0.01	10	0.00	0.00	2356	0.00	0.00	0.00	1	0.00	0.00	271	0.00	0.00	0.01	3	0.00	0.00	1187	0.01	0.00	0.01	17	0.02	0.00
299	0.00	0.00	0.00	2	0.00	0.00	2924	0.03	0.00	0.02	32	0.04	0.00	7	0.01	0.00	0.01	18	0.03	0.00	2399	0.00	0.00	0.00	4	0.00	0.00
288	0.01	0.00	0.03	8	0.11	0.01	2	0.00	0.00	0.00	1	0.00	0.00	-1	0.00	0.00	0.01	6	0.00	0.00	1096	0.00	0.00	0.00	1	0.00	0.00
4	0.00	0.00	0.00	2	0.00	0.00	2499	0.00	0.00	0.01	1	0.00	0.00	301	0.00	0.00	0.00	4	0.00	0.00	1982	0.00	0.00	0.00	1	0.00	0.00
-1	0.00	0.00	0.01	6	0.03	0.00	2921	0.00	0.00	0.00	1	0.00	0.00	36	0.00	0.00	0.01	3	0.00	0.00	2912	0.00	0.00	0.00	1	0.00	0.00
301	0.00	0.00	0.01	2	0.00	0.00	2766	0.00	0.00	0.00	1	0.00	0.00	304	0.00	0.00	0.01	2	0.00	0.00	2891	0.00	0.00	0.00	1	0.00	0.00
6	0.01	0.00	0.01	20	0.01	0.00	2989	0.00	0.00	0.01	1	0.00	0.00	147	0.00	0.00	0.00	1	0.00	0.00	2766	0.00	0.00	0.00	1	0.00	0.00
241	0.02	0.00	0.07	10	0.24	0.02	60	0.00	0.00	0.00	1	0.00	0.00	242	0.01	0.00	0.01	14	0.00	0.00	2499	0.00	0.00	0.01	1	0.00	0.00
298	0.00	0.00	0.01	1	0.00	0.00	153	0.00	0.00	0.01	4	0.00	0.00	314	0.00	0.00	0.00	4	0.00	0.00	2962	0.00	0.00	0.00	1	0.00	0.00
297	0.00	0.00	0.00	1	0.00	0.00	3637	0.00	0.00	0.00	1	0.00	0.00	66	0.00	0.00	0.01	8	0.00	0.00	2989	0.00	0.00	0.01	1	0.00	0.00
243	0.01	0.00	0.02	14	0.05	0.00	1336	0.00	0.00	0.01	1	0.00	0.00	344	0.00	0.00	0.01	8	0.00	0.00	153	0.00	0.00	0.01	8	0.00	0.00
26	0.08	0.01	0.03	79	0.06	0.01	689	0.00	0.00	0.01	1	0.00	0.00	358	0.00	0.00	0.01	8	0.00	0.00	61	0.00	0.00	0.00	3	0.00	0.00
341	0.01	0.00	0.01	14	0.02	0.00	1321	0.00	0.00	0.00	1	0.00	0.00	291	0.01	0.00	0.01	13	0.00	0.00	133	0.00	0.00	0.00	1	0.00	0.00
302	0.00	0.00	0.00	3	0.00	0.00	1327	0.00	0.00	0.01	1	0.00	0.00	198	0.03	0.00	0.02	39	0.03	0.00	3637	0.00	0.00	0.00	1	0.00	0.00
35	0.00	0.00	0.01	4	0.00	0.00	3701	0.00	0.00	0.00	1	0.00	0.00	305	0.01	0.00	0.01	13	0.02	0.00	1320	0.00	0.00	0.00	1	0.00	0.00
239	0.00	0.00	0.01	6	0.02	0.00	886	0.00	0.00	0.00	1	0.00	0.00	413	0.01	0.00	0.01	14	0.00	0.00	1336	0.00	0.00	0.00	1	0.00	0.00
311	0.00	0.00	0.01	5	0.00	0.00	1320	0.00	0.00	0.00	1	0.00	0.00	268	0.01	0.00	0.09	2	0.39	0.04	1949	0.06	0.01	0.03	61	0.05	0.01
410	0.01	0.00	0.01	9	0.00	0.00	3695	0.00	0.00	0.00	1	0.00	0.00	190	0.00	0.00	0.00	1	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00
195	0.02	0.00	0.02	28	0.03	0.00	1329	0.00	0.00	0.00	1	0.00	0.00	2484	0.00	0.00	0.01	1	0.00	0.00	3611	0.00	0.00	0.02	1	0.00	0.00
190	0.00	0.00	0.00	1	0.00	0.00	3611	0.00	0.00	0.02	1	0.00	0.00	2	0.00	0.00	0.00	1	0.00	0.00	1321	0.00	0.00	0.01	1	0.00	0.00
2766	0.00	0.00	0.00	1	0.00	0.00	1949	0.10	0.01	0.05	61	0.12	0.01	2989	0.00	0.00	0.01	1	0.00	0.00	3584	0.03	0.00	0.01	38	0.03	0.00
2962	0.00	0.00	0.00	1	0.00	0.00	1914	0.00	0.00	0.01	2	0.00	0.00	789	0.00	0.00	0.00	1	0.00	0.00	3624	0.04	0.00	0.02	50	0.05	0.00
2989	0.00	0.00	0.00	1	0.00	0.00	1916	0.01	0.00	0.01	10	0.00	0.00	2041	0.00	0.00	0.02	1	0.00	0.00	3540	0.00	0.00	0.00	1	0.00	0.00
61	0.00	0.00	0.00	1	0.00	0.00	2045	0.01	0.00	0.02	17	0.03	0.00	1990	0.00	0.00	0.02	1	0.00	0.00	3535	0.00	0.00	0.00	5	0.00	0.00
153	0.00	0.00	0.01	3	0.00	0.00	1908	0.00	0.00	0.00	2	0.00	0.00	1986	0.00	0.00	0.00	1	0.00	0.00	3583	0.02	0.00	0.01	30	0.03	0.00
1336	0.00	0.00	0.01	1	0.00	0.00	1927	0.00	0.00	0.01	2	0.00	0.00	1991	0.00	0.00	0.00	1	0.00	0.00	3568	0.08	0.01	0.03	81	0.05	0.01
689	0.00	0.00	0.01	1	0.00	0.00	1921	0.01	0.00	0.01	10	0.00	0.00	2059	0.00	0.00	0.00	1	0.00	0.00	3480	0.07	0.01	0.03	65	0.06	0.01
1321	0.00	0.00	0.01	1	0.00	0.00	2079	0.01	0.00	0.01	15	0.02	0.00	2088	0.00	0.00	0.01	1	0.00	0.00	3477	0.02	0.00	0.01	21	0.03	0.00
1327	0.00	0.00	0.00	2	0.00	0.00	2089	0.01	0.00	0.04	6	0.13	0.01	121	0.00	0.00	0.00	1	0.00	0.00	3227	0.01	0.00	0.01	16	0.00	0.00
3701	0.01	0.00	0.02	12	0.07	0.01	1948	0.06	0.01	0.02	64	0.04	0.00	744	0.00	0.00	0.00	1	0.00	0.00	3529	0.00	0.00	0.00	2	0.00	0.00
886	0.00	0.00	0.00	1	0.00	0.00	1909	0.00	0.00	0.00	1	0.00	0.00	1336	0.00	0.00	0.00	1	0.00	0.00	3482	0.05	0.00	0.02	58	0.04	0.00
422	0.00	0.00	0.01	2	0.00	0.00	1911	0.00	0.00	0.00	1	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00	3625	0.02	0.00	0.04	25	0.08	0.01
3695	0.01	0.00	0.04	3	0.20	0.02	2049	0.03	0.00	0.02	40	0.04	0.00	1321	0.00	0.00	0.00	1	0.00	0.00	3448	0.02	0.00	0.01	32	0.03	0.00
3611	0.00	0.00	0.02	1	0.00	0.00	2054	0.01	0.00	0.02	14	0.03	0.00	3701	0.01	0.00	0.03	18	0.06	0.01	3443	0.01	0.00	0.01	20	0.01	0.00
3610	0.00	0.00	0.01	1	0.00	0.00	2090	0.01	0.00	0.04	11	0.10	0.01	1338	0.00	0.00	0.00	1	0.00	0.00	3434	0.00	0.00	0.01	3	0.00	0.00
1949	0.10	0.01	0.05	54	0.11	0.01	2047	0.02	0.00	0.02	29	0.04	0.00	3695	0.01	0.00	0.03	4	0.13	0.01	3605	0.02	0.00	0.01	29	0.03	0.00
71	0.00	0.00	0.01	5	0.00	0.00	1999	0.00	0.00	0.00	1	0.00	0.00	3611	0.00	0.00	0.02	1	0.00	0.00	3450	0.00	0.00	0.01	8	0.02	0.00
31	0.00	0.00	0.01	2	0.00	0.00	1993	0.01	0.00	0.01	8	0.02	0.00	3610	0.00	0.00	0.01	1	0.00	0.00	3587	0.00	0.00	0.00	8	0.00	0.00
68	0.00	0.00	0.01	6	0.02	0.00	2004	0.00	0.00	0.00	4	0.00	0.00	1949	0.10	0.01	0.05	61	0.10	0.01	13	0.00	0.00	0.01	6	0.00	0.00
60	0.00	0.00	0.01	2	0.00	0.00	1887	0.01	0.00	0.01	14	0.01	0.00	32	0.00	0.00	0.00	3	0.00	0.00	422	0.01	0.00	0.01	17	0.02	0.00
37	0.00	0.00	0.00	1	0.00	0.00	2055	0.00	0.00	0.01	6	0.00	0.00	72	0.00	0.00	0.01	6	0.02	0.00	427	0.00	0.00	0.00	2	0.00	0.00
35	0.00	0.00	0.00	1	0.00	0.00	260	0.01	0.00	0.01	7	0.03	0.00	41	0.00	0.00	0.00	2	0.00	0.00	-1	0.00	0.00	0.00	9	0.00	0.00
50	0.00	0.00	0.01	2	0.00	0.00	55	0.00	0.00	0.00	3	0.00	0.00	39	0.01	0.00	0.01	9	0.00	0.00	495	0.00	0.00	0.01	4	0.03	0.00
374	0.00	0.00	0.00	1	0.00	0.00	635	0.00	0.00	0.00	1	0.00	0.00	69	0.01	0.00	0.01	14	0.01	0.00	109	0.09	0.01	0.03	81	0.06	0.01
62	0.00	0.00	0.01	5	0.00	0.00	76	0.00	0.00	0.01	6	0.00	0.00	73	0.00	0.00	0.00	1	0.00	0.00	438	0.01	0.00	0.02	19	0.03	0.00
257	0.00	0.00	0.01	6	0.00	0.00	45	0.01	0.00	0.01	10	0.02	0.00	63	0.00	0.00	0.01	2	0.00	0.00	651	0.00	0.00	0.01	2	0.00	0.00
40	0.00	0.00	0.01	5	0.00	0.00	43	0.00	0.00	0.01	6	0.00	0.00	645	0.00	0.00	0.00	1	0.00	0.00	509	0.01	0.00	0.04	3	0.19	0.02
38	0.00	0.00	0.01	6	0.02	0.00	65	0.00	0.00	0.01	3	0.00	0.00	70	0.00	0.00	0.01	2	0.00	0.00	216	0.00	0.00	0.00	2	0.00	0.00
764	0.00	0.00	0.00	1	0.00	0.00	540	0.00	0.00	0.00	1	0.00	0.00	259	0.00	0.00	0.01	5	0.00	0.00	514	0.00	0.00	0.00	1	0.00	0.00
1824	0.00	0.00	0.01	1	0.00	0.00	67	0.00	0.00	0.01	4	0.00	0.00	61	0.00	0.00	0.01	3	0.00	0.00	75	0.03	0.00	0.02	31	0.05	0.00
2145	0.00	0.00	0.00	1	0.00	0.00	42	0.00	0.00	0.00	4	0.00	0.00	36	0.00	0.00	0.01	3	0.00	0.00	530	0.00	0.00	0.01	5	0.00	0.00
746	0.00	0.00	0.00	1	0.00	0.00	40	0.01	0.00	0.01	11	0.00	0.00	97	0.00	0.00	0.00	1	0.00	0.00	749	0.08	0.01	0.02	79	0.04	0.00
1802	0.00	0.00	0.01	1	0.00	0.00	73	0.02	0.00	0.01	25	0.02	0.00	153	0.01	0.00	0.01	13	0.00	0.00	101	0.00	0.00	0.00	1	0.00	0.00
2053	0.00	0.00	0.00	1	0.00	0.00	234	0.00	0.00	0.01	8	0.00	0.00	290	0.01	0.00	0.01	13	0.02	0.00	540	0.00	0.00	0.00	1	0.00	0.00
2098	0.00	0.00	0.01	1	0.00	0.00	148	0.00	0.00	0.00	1	0.00	0.00	636	0.08	0.01	0.03	68	0.06	0.01	539	0.00	0.00	0.00	1	0.00	0.00
2052	0.00	0.00	0.00	1	0.00	0.00	296	0.00	0.00	0.00	1	0.00	0.00								741	0.00	0.00	0.00	3	0.00	0.00
1821	0.00	0.00	0.00	1	0.00	0.00	29	0.10	0.01	0.03	79	0.06	0.01								117	0.00	0.00	0.00	5	0.00	0.00
2050	0.00	0.00	0.00	1	0.00	0.00	264	0.02	0.00	0.07	8	0.33	0.03								305	0.03	0.00	0.02	41	0.03	0.00
290	0.01	0.00	0.01	10	0.02	0.00	294	0.00	0.00	0.00	1	0.00	0.00								599	0.00	0.00	0.00	1	0.00	0.00
636	0.10	0.01	0.04	77	0.08	0.01	69	0.00	0.00	0.01	5	0.00	0.00								515	0.01	0.00	0.01	16	0.00	0.00
							353	0.01	0.00	0.01	13	0.00	0.00								740	0.00	0.00	0.01	6	0.00	0.00
							268	0.00	0.00	0.00	6	0.00	0.00								721	0.01	0.00	0.01	17	0.02	0.00
							33	0.00	0.00	0.01	1	0.00	0.00								555	0.00	0.00	0.00	1	0.00	0.00
							-1	0.00	0.00	0.01	3	0.00	0.00								653	0.01	0.00	0.01	16	0.02	0.00
							301	0.00	0.00	0.01	7	0.00	0.00								637	0.00	0.00	0.02	3	0.06	0.01
							7	0.00	0.00	0.01	5	0.00	0.00								553	0.01	0.00	0.01	20	0.00	0.00
							240	0.02	0.00	0.02	29	0.04	0.00								430	0.02	0.00	0.04	24	0.07	0.01
							300	0.00	0.00	0.00	1	0.00	0.00								582	0.00	0.00	0.01	7	0.00	0.00
							267	0.00	0.00	0.01	5	0.00	0.00								419	0.00	0.00	0.01	4	0.03	0.00
							298	0.00	0.00	0.01	4	0.00	0.00								541	0.00	0.00	0.00	4	0.00	0.00
							192	0.03	0.00	0.02	35	0.04	0.00								575	0.00	0.00	0.01	5	0.00	0.00
							68	0.00	0.00	0.00	1	0.00	0.00								957	0.01	0.00	0.01	13	0.01	0.00
							310	0.01	0.00	0.01	12	0.02	0.00								391	0.00	0.00	0.00	2	0.00	0.00
							37	0.09	0.01	0.04	76	0.07	0.01								75	0.00	0.00	0.01	2	0.00	0.00
							236	0.03	0.00	0.07	18	0.21	0.02								56	0.00	0.00	0.01	2	0.00	0.00
							339	0.01	0.00	0.01	11	0.00	0.00								387	0.00	0.00	0.01	5	0.00	0.00
							9	0.01	0.00	0.01	21	0.02	0.00								397	0.01	0.00	0.01	18	0.02	0.00
							287	0.01	0.00	0.04	13	0.12	0.01								44	0.00	0.00	0.00	6	0.00	0.00
							408	0.01	0.00	0.01	9	0.00	0.00								399	0.00	0.00	0.01	8	0.00	0.00
																					77	0.00	0.00	0.00	4	0.00	0.00
																					261	0.01	0.00	0.01	14	0.01	0.00
																					68	0.00	0.00	0.01	1	0.00	0.00
																					43	0.00	0.00	0.01	8	0.00	0.00
																					66	0.00	0.00	0.00	1	0.00	0.00
																					74	0.00	0.00	0.01	1	0.00	0.00
																					204	0.00	0.00	0.00	1	0.00	0.00
																					-1	0.00	0.00	0.01	2	0.00	0.00
																					46	0.00	0.00	0.00	5	0.00	0.00
																					543	0.00	0.00	0.00	4	0.00	0.00
																					37	0.00	0.00	0.01	5	0.02	0.00
																					41	0.01	0.00	0.01	10	0.02	0.00

▶quants.c: 1011 - 76.39 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default	Run aocc_8	Run icx_1
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1011-1013 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1077 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
			771	76.39	7.23	8.31	96	10.04	0.95

▶ops.cpp: 8690 - 1.16 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default							Run aocc_8	Run icx_1
		/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 370-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 486-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 671-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 736-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130								/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 392-393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 693-694 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 756-757 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
	332	0.26	0.02	0.10	75	0.23	0.02		707	0.90	0.08	0.19	76	0.56	0.05

▶vec.cpp: 331 - 0.71 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default	Run aocc_8	Run icx_1
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
			505	0.71	0.07	0.16	64	0.30	0.03

▶ggml-cpu.c: 533 - 0.64 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default	Run aocc_8	Run icx_1
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1147 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1234 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1242-1260 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1295 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1328 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1365-1379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397
			99	0.64	0.06	0.13	96	0.26	0.02

▶ops.cpp: 6210 - 0.62 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run icx_default							Run aocc_8							Run icx_1
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6331 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6338-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6389-6447 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6456-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6258-6276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6285-6285 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6296-6303 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6399-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6331 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6338-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6389-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6258-6276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6285-6288 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6296-6303 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6399-6447 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6456-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490
313	0.14	0.01	0.05	84	0.09	0.01	312	0.16	0.01	0.05	86	0.11	0.01	316	0.18	0.02	0.04	93	0.09	0.01	669	0.15	0.01	0.04	90	0.09	0.01

▶ops.cpp: 8692 - 0.53 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default	Run aocc_8							Run icx_1
	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8692-8692 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8700-8700 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 375-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 673-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 740-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130								/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8692-8692 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8700-8700 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 375-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 740-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
334	0.27	0.03	0.08	72	0.19	0.02		337	0.26	0.02	0.08	68	0.18	0.02

▶quants.c: 293 - 0.46 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default							Run aocc_8							Run icx_1
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 293-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 386-386							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 293-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 386-386							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 293-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 386-386
478	0.16	0.01	0.04	89	0.08	0.01	476	0.16	0.01	0.04	85	0.09	0.01	481	0.14	0.01	0.04	86	0.10	0.01

▶vec.cpp: 304 - 0.27 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default	Run aocc_8							Run icx_1
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130								/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
263	0.14	0.01	0.05	62	0.12	0.01		266	0.13	0.01	0.06	60	0.12	0.01

▶ggml-quants.c: 199 - 0.19 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default	Run aocc_8	Run icx_1
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-quants.c: 199-222 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 389-404
			1036	0.19	0.02	0.04	93	0.10	0.01

▶vec.cpp: 207 - 0.14 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default	Run icx_default							Run aocc_8	Run icx_1
		/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 207-207 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
	262	0.14	0.01	0.05	61	0.12	0.01

▶Old Layout

Functions

Name	Module	Coverage (%)	Inclusive Time w.r.t. Wall Time(s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (coverage)	Deviation (time)
Name	Module	orig_default	icx_default	aocc_8	icx_1	orig_default	icx_default	aocc_8	icx_1	orig_default	icx_default	aocc_8	icx_1	orig_default	icx_default	aocc_8	icx_1	orig_default	icx_default	aocc_8	icx_1	orig_default	icx_default	aocc_8	icx_1
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<2>(long, long, long, long)	libggml-cpu.so	65.97	65.33	65.38	NA	6.10	6.04	6.03	NA	8.32	8.33	8.28	NA	96	96	96	NA	22.54	22.45	22.68	NA	2.10	2.09	2.10	NA
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	76.39	NA	NA	NA	7.23	NA	NA	NA	8.31	NA	NA	NA	96	NA	NA	NA	10.04	NA	NA	NA	0.95
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libiomp5.so	NA	31.36	NA	19.11	NA	2.90	NA	1.81	NA	8.11	NA	3.31	NA	96	NA	96	NA	21.95	NA	9.31	NA	2.00	NA	0.87
__kmp_hardware_timestamp	libomp.so	17.27	NA	17.67	NA	1.60	NA	1.63	NA	4.55	NA	4.66	NA	96	NA	96	NA	12.32	NA	12.51	NA	1.12	NA	1.14	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	14.42	NA	14.27	NA	1.33	NA	1.32	NA	3.78	NA	3.61	NA	96	NA	96	NA	10.39	NA	10.06	NA	0.95	NA	0.91	NA
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long)	libggml-cpu.so	0.49	0.58	0.56	NA	0.05	0.05	0.05	NA	0.07	0.08	0.08	NA	96	96	96	NA	0.19	0.20	0.18	NA	0.02	0.02	0.02	NA
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libiomp5.so	NA	0.89	NA	0.62	NA	0.08	NA	0.06	NA	0.22	NA	0.14	NA	96	NA	96	NA	0.61	NA	0.33	NA	0.06	NA	0.03
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libomp.so	0.55	NA	0.78	NA	0.05	NA	0.07	NA	1.29	NA	2.43	NA	89	NA	92	NA	1.56	NA	3.07	NA	0.14	NA	0.28	NA
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	NA	NA	NA	0.90	NA	NA	NA	0.08	NA	NA	NA	0.19	NA	NA	NA	76	NA	NA	NA	0.56	NA	NA	NA	0.05
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	0.27	0.26	0.26	0.00	0.03	0.02	0.02	0.00	0.08	0.10	0.08	0.01	72	75	68	5	0.19	0.23	0.18	0.00	0.02	0.02	0.02	0.00
ggml_vec_dot_f16	libggml-cpu.so	NA	NA	NA	0.71	NA	NA	NA	0.07	NA	NA	NA	0.16	NA	NA	NA	64	NA	NA	NA	0.30	NA	NA	NA	0.03
ggml_compute_forward_mul_mat	libggml-cpu.so	NA	NA	NA	0.64	NA	NA	NA	0.06	NA	NA	NA	0.13	NA	NA	NA	96	NA	NA	NA	0.26	NA	NA	NA	0.02
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.14	0.16	0.18	0.00	0.01	0.01	0.02	0.00	0.05	0.05	0.04	0.00	84	86	93	1	0.09	0.11	0.09	0.00	0.01	0.01	0.01	0.00
quantize_row_q8_0	libggml-cpu.so	0.16	0.16	0.14	0.00	0.01	0.01	0.01	0.00	0.04	0.04	0.04	0.00	89	85	86	3	0.08	0.09	0.10	0.00	0.01	0.01	0.01	0.00
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libiomp5.so	NA	0.22	NA	0.21	NA	0.02	NA	0.02	NA	0.09	NA	0.10	NA	93	NA	80	NA	0.20	NA	0.26	NA	0.02	NA	0.02
ggml_vec_dot_f16	libggml-cpu.so	0.14	0.14	0.13	0.00	0.01	0.01	0.01	0.00	0.05	0.05	0.06	0.01	62	61	60	4	0.12	0.12	0.12	0.03	0.01	0.01	0.01	0.00
__GI___sched_yield	libc.so.6	0.10	0.10	0.10	0.06	0.01	0.01	0.01	0.01	0.05	0.05	0.05	0.03	54	61	61	61	0.11	0.12	0.10	0.05	0.01	0.01	0.01	0.01
ggml_compute_forward_mul_mat	libggml-cpu.so	0.08	0.10	0.09	NA	0.01	0.01	0.01	NA	0.03	0.03	0.04	NA	79	79	77	NA	0.06	0.06	0.07	NA	0.01	0.01	0.01	NA
ggml_graph_compute_thread	libggml-cpu.so	0.07	0.09	0.07	NA	0.01	0.01	0.01	NA	0.03	0.04	0.03	NA	69	76	70	NA	0.05	0.07	0.06	NA	0.00	0.01	0.01	NA
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.19	NA	NA	NA	0.02	NA	NA	NA	0.04	NA	NA	NA	93	NA	NA	NA	0.10	NA	NA	NA	0.01
f64xsubf128	libm.so.6	0.10	NA	0.08	NA	0.01	NA	0.01	NA	0.04	NA	0.03	NA	77	NA	68	NA	0.08	NA	0.06	NA	0.01	NA	0.01	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libiomp5.so	NA	0.08	NA	0.07	NA	0.01	NA	0.01	NA	0.14	NA	0.08	NA	31	NA	35	NA	0.32	NA	0.21	NA	0.03	NA	0.02
ggml_compute_forward_rope_f32	libggml-cpu.so	NA	NA	NA	0.15	NA	NA	NA	0.01	NA	NA	NA	0.04	NA	NA	NA	90	NA	NA	NA	0.09	NA	NA	NA	0.01
__libm_sse2_sincosf_l9	binary	NA	0.06	NA	0.07	NA	0.01	NA	0.01	NA	0.02	NA	0.03	NA	64	NA	65	NA	0.04	NA	0.06	NA	0.00	NA	0.01
ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	0.02	0.03	0.03	0.03	0.00	0.00	0.00	0.00	0.02	0.02	0.02	0.02	28	35	39	41	0.03	0.04	0.03	0.03	0.00	0.00	0.00	0.00
ggml_graph_compute_thread	libggml-cpu.so	NA	NA	NA	0.09	NA	NA	NA	0.01	NA	NA	NA	0.03	NA	NA	NA	81	NA	NA	NA	0.06	NA	NA	NA	0.01
__libm_roundf_y8	binary	NA	NA	NA	0.08	NA	NA	NA	0.01	NA	NA	NA	0.03	NA	NA	NA	81	NA	NA	NA	0.05	NA	NA	NA	0.01
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	0.08	NA	NA	NA	0.01	NA	NA	NA	0.02	NA	NA	NA	79	NA	NA	NA	0.04	NA	NA	NA	0.00
__libm_powf_l9	binary	NA	0.03	NA	0.03	NA	0.00	NA	0.00	NA	0.02	NA	0.01	NA	40	NA	38	NA	0.04	NA	0.03	NA	0.00	NA	0.00
ggml_compute_forward_mul	libggml-cpu.so	0.01	0.02	0.03	0.00	0.00	0.00	0.00	0.00	0.02	0.02	0.04	0.00	14	29	35	2	0.05	0.04	0.06	0.00	0.00	0.00	0.01	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.02	0.03	0.02	NA	0.00	0.00	0.00	NA	0.07	0.07	0.04	NA	10	18	18	NA	0.24	0.21	0.12	NA	0.02	0.02	0.01	NA
__libm_logf_l9	binary	NA	0.01	NA	0.05	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	14	NA	58	NA	0.03	NA	0.04	NA	0.00	NA	0.00
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	libiomp5.so	NA	0.03	NA	0.03	NA	0.00	NA	0.00	NA	0.04	NA	0.05	NA	21	NA	21	NA	0.10	NA	0.13	NA	0.01	NA	0.01
__intel_avx_rep_memcpy	binary	NA	0.01	NA	0.04	NA	0.00	NA	0.00	NA	0.04	NA	0.02	NA	6	NA	50	NA	0.13	NA	0.05	NA	0.01	NA	0.00
ggml_vec_swiglu_f32	libggml-cpu.so	0.01	0.02	0.01	NA	0.00	0.00	0.00	NA	0.09	0.07	0.09	NA	4	8	2	NA	0.44	0.33	0.39	NA	0.04	0.03	0.04	NA
__kmp_yield	libiomp5.so	NA	0.03	NA	0.02	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	32	NA	29	NA	0.04	NA	0.03	NA	0.00	NA	0.00
__kmp_barrier	libiomp5.so	NA	0.02	NA	0.03	NA	0.00	NA	0.00	NA	0.03	NA	0.04	NA	26	NA	34	NA	0.05	NA	0.07	NA	0.00	NA	0.01
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.01	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	20	21	18	6	0.01	0.02	0.03	0.00	0.00	0.00	0.00	0.00
__libm_log2_l9	binary	NA	0.02	NA	0.02	NA	0.00	NA	0.00	NA	0.02	NA	0.01	NA	29	NA	21	NA	0.04	NA	0.03	NA	0.00	NA	0.00
int __kmp_barrier_template<false>(barrier_type, int, int, unsigned long, void, void ()(void, void)) [clone .isra.33]	libomp.so	0.02	NA	0.02	NA	0.00	NA	0.00	NA	0.04	NA	0.01	NA	22	NA	27	NA	0.09	NA	0.03	NA	0.01	NA	0.00	NA
__libm_expf_l9	binary	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.02	NA	0.01	NA	17	NA	30	NA	0.03	NA	0.03	NA	0.00	NA	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	0.01	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.03	0.04	0.01	0.01	8	13	13	5	0.11	0.12	0.00	0.00	0.01	0.01	0.00	0.00
__intel_avx_rep_memset	binary	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.04	NA	0.04	NA	11	NA	25	NA	0.10	NA	0.08	NA	0.01	NA	0.01
powf	binary	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	10	NA	32	NA	0.00	NA	0.03	NA	0.00	NA	0.00
ggml_is_empty	libggml-base.so	0.00	0.02	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	6	25	14	1	0.02	0.02	0.01	0.00	0.00	0.00	0.00	0.00
__memset_avx512_unaligned_erms	libc.so.6	0.01	0.00	0.01	NA	0.00	0.00	0.00	NA	0.02	0.00	0.03	NA	12	1	18	NA	0.07	0.00	0.06	NA	0.01	0.00	0.01	NA
ggml_cpu_fp32_to_fp16	libggml-cpu.so	NA	NA	NA	0.03	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	31	NA	NA	NA	0.05	NA	NA	NA	0.00
ggml_compute_forward_rope	libggml-cpu.so	0.00	0.01	0.00	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.01	5	12	4	20	0.00	0.02	0.00	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_glu	libggml-cpu.so	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	14	11	8	7	0.02	0.00	0.00	0.00	0.00	0.00	0.00	0.00
_intel_fast_memcpy	binary	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	29	NA	NA	NA	0.03	NA	NA	NA	0.00
llamafile_sgemm	libggml-cpu.so	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	10	13	8	6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.04	NA	NA	NA	24	NA	NA	NA	0.07	NA	NA	NA	0.01
ggml_rope_yarn_corr_dims	libggml-base.so	0.00	0.01	0.00	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	6	7	5	14	0.00	0.03	0.00	0.01	0.00	0.00	0.00	0.00
ggml_cpu_extra_compute_forward	libggml-cpu.so	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	6	8	14	4	0.02	0.00	0.00	0.03	0.00	0.00	0.00	0.00
(anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::mnpack(long, long, long, long)	libggml-cpu.so	0.01	0.01	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	9	9	14	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__svml_logf4_l9	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	14	NA	16	NA	0.01	NA	0.00	NA	0.00	NA	0.00
logf	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	10	NA	20	NA	0.00	NA	0.01	NA	0.00	NA	0.00
ggml_compute_forward_add	libggml-cpu.so	0.00	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.01	0.00	0.01	0.01	3	6	4	16	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_type_size	libggml-base.so	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	6	6	9	6	0.02	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__tls_get_addr	ld-linux-x86-64.so.2	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	3	4	13	8	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_nrows	libggml-base.so	0.00	0.01	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	1	11	3	10	0.00	0.00	0.00	0.02	0.00	0.00	0.00	0.00
unknown_function	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	6	3	6	9	0.03	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__log2_finite	libm.so.6	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	10	NA	13	NA	0.02	NA	0.02	NA	0.00	NA	0.00	NA
__kmpc_barrier	libiomp5.so	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	6	NA	17	NA	0.00	NA	0.02	NA	0.00	NA	0.00
ggml_compute_forward_set_rows	libggml-cpu.so	0.00	0.00	0.01	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	3	7	13	NA	0.00	0.00	0.02	NA	0.00	0.00	0.00	NA
ggml_compute_forward_mul	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	19	NA	NA	NA	0.03	NA	NA	NA	0.00
__memcpy_avx512_unaligned_erms	libc.so.6	0.01	0.00	0.01	NA	0.00	0.00	0.00	NA	0.04	0.00	0.03	NA	3	1	4	NA	0.20	0.00	0.13	NA	0.02	0.00	0.01	NA
ggml_row_size	libggml-base.so	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.00	5	10	2	5	0.00	0.02	0.00	0.00	0.00	0.00	0.00	0.00
ggml_can_repeat	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	5	6	6	4	0.00	0.00	0.02	0.00	0.00	0.00	0.00	0.00
ggml_backend_cpu_get_extra_buffer_types()	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	4	5	8	5	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_cpu_extra_compute_forward	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	17	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_is_empty	libggml-base.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	18	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_compute_forward_glu	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	17	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_compute_forward_set_rows	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	16	NA	NA	NA	0.02	NA	NA	NA	0.00
__kmpc_barrier	libomp.so	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	6	NA	11	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
_intel_fast_memset	binary	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	15	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA
__memcmp_evex_movbe	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.02	0.02	0.02	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_vec_swiglu_f32	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.04	NA	NA	NA	3	NA	NA	NA	0.19	NA	NA	NA	0.02
__libm_exp2f_z0	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	6	NA	8	NA	0.00	NA	0.00	NA	0.00	NA	0.00
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	13	NA	NA	NA	0.01	NA	NA	NA	0.00
ggml_blck_size	libggml-base.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	1	4	NA	8	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__kmp_get_global_thread_id_reg	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	4	NA	8	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_is_contiguous_1	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	5	4	2	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__libm_ceilf_y8	binary	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	8	NA	2	NA	0.02	NA	0.00	NA	0.00	NA	0.00
ggml_get_type_traits	libggml-base.so	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	0.01	2	NA	3	5	0.00	NA	0.00	0.02	0.00	NA	0.00	0.00
__kmp_resume_if_soft_paused	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	4	NA	6	NA	0.00	NA	0.02	NA	0.00	NA	0.00
llama_vocab::impl::~impl()	libllama.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.02	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
_IO_fread	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_task_team_sync	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	6	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_permute	libggml-cpu.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	2	4	NA	4	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__kmp_task_team_sync	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	5	NA	0.00	NA	0.02	NA	0.00	NA	0.00	NA
ggml_get_type_traits_cpu	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	2	5	2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_compute_forward_dup	libggml-cpu.so	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.00	NA	5	3	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
ggml_is_contiguous	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	2	3	3	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
roundf	binary	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	8	NA	NA	NA	0.02	NA	NA	NA	0.00
__GI___libc_malloc	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_can_repeat	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	8	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_graph_compute.omp_outlined	libggml-cpu.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	4	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::compare(char const*) const	libstdc++.so.6.0.29	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_get_glu_op	libggml-base.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.00	NA	0.01	2	3	NA	2	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
.plt.sec@start	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	3	NA	NA	NA	0.06	NA	NA	NA	0.01
ggml_compute_forward_view	libggml-cpu.so	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	0.00	1	NA	4	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
malloc_consolidate	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_get_global_thread_id_reg	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__libm_expf_e7	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	5	NA	0.00	NA	0.00	NA	0.00	NA	0.00
std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, unsigned char>, s...	libllama.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_compute_forward_get_rows	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.01	NA	2	1	2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
_int_free	libc.so.6	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	2	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
exp2f	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	2	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_is_contiguous	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	5	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNKSt10_HashtableISt4pairINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES6_ES0_IKS7_iESaIS9_ENSt8__detail10_Select1stESt8equal_toIS7_EN11llama_vocab4impl9pair_hashENSB_18_Mod_range_hashingENSB_20_Default_ranged_hashENSB_20_Prime_rehash_policyENSB_17...	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__kmp_invoke_task_func	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_invoke_microtask	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
OmptReturnAddressGuard::OmptReturnAddressGuard(int, void*)	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__memchr_evex	libc.so.6	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__libm_floorf_y8	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	4	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_compute_forward_reshape	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_are_same_shape	libggml-base.so	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.01	NA	NA	2	2	NA	NA	0.00	0.00	NA	NA	0.00	0.00
ggml_backend_cpu_repack_buffer_type()	libggml-cpu.so	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	1	1	2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
std::basic_ostream<char, std::char_traits<char> >& std::__ostream_insert<char, std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*, long)	libstdc++.so.6.0.29	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_launch_thread	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_init_implicit_task	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00
_dl_lookup_symbol_x	ld-linux-x86-64.so.2	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	1	NA	NA	3	0.00	NA	NA	0.00	0.00	NA	NA	0.00
ggml_rope_yarn_corr_dims	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	4	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZN11llama_vocab4implD2Ev.A	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_yield	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_join_barrier(int)	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_enter_single	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_graph_plan	libggml-cpu.so	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	libstdc++.so.6.0.29	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	1	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__kmp_invoke_task_func	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	3	NA	NA	NA	0.00	NA	NA	NA	0.00
sched_yield@plt	libomp.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
std::ostream::sentry::sentry(std::ostream&)	libstdc++.so.6.0.29	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
.plt.sec@start	libstdc++.so.6.0.29	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
gguf_get_arr_str	libggml-base.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.29	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::pair<std::__detail::_Node_iterator<std::pair<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<c...	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
log2	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__libm_sse2_sincosf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
_IO_file_xsgetn	libc.so.6	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
llama_decode_text(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
llama_vocab::impl::load(llama_model_loader&, LLM_KV const&)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__GI___call_tls_dtors	libc.so.6	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
unlink_chunk.constprop.0	libc.so.6	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_enter_single	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__strlen_evex	libc.so.6	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::find(char const*, unsigned long, unsigned long) const	libstdc++.so.6.0.29	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
__kmpc_global_thread_num	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNSt8__detail9_Map_baseINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEESt4pairIKS6_iESaIS9_ENS_10_Select1stESt8equal_toIS6_ESt4hashIS6_ENS_18_Mod_range_hashingENS_20_Default_ranged_hashENS_20_Prime_rehash_policyENS_17_Hashtable_traitsILb1ELb0ELb1EEEL...	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_get_rows	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
unknown_function	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_is_contiguous_1	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, std::alloca...	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
ggml_init	libggml-base.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
_dl_fixup	ld-linux-x86-64.so.2	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__kmp_fork_barrier(int, int)	libomp.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
unicode_utf8_to_byte(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__GI___libc_free	libc.so.6	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
replace_all(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<...	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
llama_kv_cache::set_input_kq_mask(ggml_tensor, llama_ubatch const, bool) const	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
llama_batch_allocr::clear()	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
ggml_compute_forward_cpy	libggml-cpu.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_graph_compute.extracted	libggml-cpu.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_finish_implicit_task	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
expf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_invoke_microtask	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::resize(unsigned long, char)	libstdc++.so.6.0.29	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
unicode_cpts_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
floorf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
std::__detail::_Map_base<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, st...	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_critical_section_start	libggml-base.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
unicode_cpt_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, unsigned long&)	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
_int_malloc	libc.so.6	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
do_lookup_x	ld-linux-x86-64.so.2	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_api_omp_get_thread_num	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_gallocr_reserve_n	libggml-base.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmp_launch_thread	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
gguf_kv_to_str[abi:cxx11](gguf_context const*, int)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
llama_kv_cache::prepare(std::vector<llama_ubatch, std::allocator<llama_ubatch> > const&)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmpc_global_thread_num	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmp_finish_implicit_task	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
llama_vocab::impl::token_to_piece(int, char*, int, int, bool) const	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmp_task_team_wait	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmp_initialize_info(kmp_info, kmp_team, int, int)	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_fork_barrier(int, int)	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_add	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_mul_mat	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_join_barrier(int)	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNK11llama_vocab4impl24token_to_piece_for_cacheB5cxx11Eib.A	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
llama_decode_text	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_replace_aux(unsigned long, unsigned long, unsigned long, char)	libstdc++.so.6.0.29	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_dl_runtime_resolve_xsavec	ld-linux-x86-64.so.2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::reserve(unsigned long)	libstdc++.so.6.0.29	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__libm_floor_y8	binary	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
unicode_cpt_to_utf8	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_graph_plan	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00

	orig_default	icx_default	aocc_8	icx_1
Uncheck all modules
libggml-cpu.so	67.46 %	66.99 %	66.97 %	79.14 %
libomp.so	32.28 %	0.00 %	32.77 %
libiomp5.so
binary
libc.so.6	0.13 %	0.11 %	0.13 %	0.06 %
libggml-base.so	0.02 %	0.05 %	0.03 %	0.26 %
libm.so.6	0.10 %	0.00 %	0.08 %
libllama.so	0.01 %	0.01 %	0.01 %	0.01 %
ld-linux-x86-64.so.2	0.00 %	0.00 %	0.01 %	0.01 %
libstdc++.so.6.0.29	0.00 %	0.00 %	0.00 %	0.00 %

Report Configuration

Functions

▶sgemm.cpp: 138 - 198.30 %

▶<unknown>: 0 - 120.58 %

▶quants.c: 1011 - 76.39 %

▶ops.cpp: 8690 - 1.16 %

▶vec.cpp: 331 - 0.71 %

▶ggml-cpu.c: 533 - 0.64 %

▶ops.cpp: 6210 - 0.62 %

▶ops.cpp: 8692 - 0.53 %

▶quants.c: 293 - 0.46 %

▶vec.cpp: 304 - 0.27 %

▶ggml-quants.c: 199 - 0.19 %

▶vec.cpp: 207 - 0.14 %

▶Old Layout

▶Filters

Functions